检索结果-内蒙古大学图书馆

An Improved Algorithm for Spiking Neural Networks with Multi-Scale Attention Coding

学校读者我要写书评

暂无评论

An Improved Algorithm for Spiking Neural Networks with Multi...

Cyber-Physical Social intelligence (ICCSI), International Conference on

作者： Sisi Chen Xiaofeng Chen Weikai Li Department of Mathematics Chongqing Jiaotong University Chongqing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

ISBN: (数字)9798350376739

ISBN: (纸本)9798350376746

Spiking Neural Networks (SNNs), driven by spike-based mechanisms, are known for their high efficiency and low energy consumption, which makes them ideal for applications like image classification, object detection, and medical diagnostics. However, challenges include training difficulties due to the non-differentiability of spiking activities and limitations in encoding schemes, which struggle to capture complex spatio-temporal dynamics. In this paper, we propose a novel algorithm, termed the Spatio-Temporal Backpropagation algorithm with Multi-Scale Attention Coding (STBP-MSC). STBP-MSC dynamically allocates attention across spatial and temporal domains, which improves coding efficiency and enhances the classification accuracy of SNNs. Furthermore, STBP-MSC incorporates the Complementary Leaky Integrate-and-Fire (CLIF) neuron model, which enhances temporal gradient computation. Experimental results on the MNIST and Fashion-MNIST datasets demonstrate that STBP-MSC achieves high coding efficiency and superior performance within minimal time windows.

关键词： Training Visualization Heuristic algorithms Computational modeling Neurons Spiking neural networks Backpropagation algorithms Encoding Classification algorithms Medical diagnosis

Unlocking the Power of Open Set: A New Perspective for Open-Set Noisy Label Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wan, Wenhai Wang, Xinrui Xie, Ming-Kun Li, Shao-Yuan Huang, Sheng-Jun Chen, Songcan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

Learning from noisy data has attracted much attention, where most methods focus on closed-set label noise. However, a more common scenario in the real world is the presence of both open-set and closed-set noise. Existing methods typically identify and handle these two types of label noise separately by designing a specific strategy for each type. However, in many real-world scenarios, it would be challenging to identify open-set examples, especially when the dataset has been severely corrupted. Unlike the previous works, we explore how models behave when faced with open-set examples, and find that a part of open-set examples gradually get integrated into certain known classes, which is beneficial for the separation among known classes. Motivated by the phenomenon, we propose a novel two-step contrastive learning method CECL (Class Expansion Contrastive Learning) which aims to deal with both types of label noise by exploiting the useful information of open-set examples. Specifically, we incorporate some open-set examples into closed-set classes to enhance performance while treating others as delimiters to improve representative ability. Extensive experiments on synthetic and real-world datasets with diverse label noise demonstrate the effectiveness of CECL. Copyright © 2023, The Authors. All rights reserved.

关键词： machine learning

Label-aware global consistency for multi-label learning with single positive labels 22

学校读者我要写书评

暂无评论

Label-aware global consistency for multi-label learning with...

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Ming-Kun Xie Jia-Hao Xiao Sheng-Jun Huang College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing

ISBN: (纸本)9781713871088

In single positive multi-label learning (SPML), only one of multiple positive labels is observed for each instance. The previous work trains the model by simply treating unobserved labels as negative ones, and designs the regularization to constrain the number of expected positive labels. However, in many real-world scenarios, the true number of positive labels is unavailable, making such methods less applicable. In this paper, we propose to solve SPML problems by designing a Label-Aware global Consistency (LAC) regularization, which leverages the manifold structure information to enhance the recovery of potential positive labels. On one hand, we first perform pseudo-labeling for each unobserved label based on its prediction probability. The consistency regularization is then imposed on model outputs to balance the fitting of identified labels and exploring of potential positive labels. On the other hand, by enforcing label-wise embeddings to maintain global consistency, LAC loss encourages the model to learn more distinctive representations, which is beneficial for recovering the information of potential positive labels. Experiments on multiple benchmark datasets validate that the proposed method can achieve state-of-the-art performance for solving SPML tasks.

关键词：

A Multilayer Maximum Spanning Tree Kernel For Brain Networks

学校读者我要写书评

暂无评论

A Multilayer Maximum Spanning Tree Kernel For Brain Networks

IEEE International Symposium on Biomedical Imaging

作者： Xiaoxin Wang Xuyun Wen Kai Ma Daoqiang Zhang MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China

ISBN: (纸本)9781665412469;9781665429474

The brain network has been widely used for the construction of diverse brain disease diagnosis models. Among these models, an important and challenging task is how to quantify the network similarity. Although many graph kernels have been proposed for estimating topological similarity of a pair of networks, most of them ignore the global structure of networks by only focusing on subgraphs (i.e., a subset of original graph). To address this issue, we propose a novel multilayer graph kernel method based on maximum spanning tree (MST) for measuring the similarity of pair-wise brain networks. For two given networks, the proposed kernel estimates their similarity at each layer of MST generation to capture the topological properties of brain networks from local to global levels. Meanwhile, since the construction of MST is completely data-driven, MST based kernel can retain individual differences without destroying the individual inherent connectivity patterns. To validate our method, we apply our proposed graph kernel to the classifications of mild cognitive impairment (MCI). Experimental results demonstrate that our method outperforms the state-of-the-art graph kernel methods.

关键词： Focusing Biomedical measurement Nonhomogeneous media Brain modeling Medical diagnosis Kernel Task analysis

Research on Indoor Passive Location Based on LoRa Fingerprint 1

学校读者我要写书评

暂无评论

6th EAI International Conference on machine Learning and Intelligent Communications, MLICOM 2021

作者： Wang, Heng Chen, Yuzhen Zhang, Qingheng Zhang, Shifan Ye, Haibo Li, Xuan-Song School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

ISBN: (数字)9783031044090

ISBN: (纸本)9783031044083

Indoor positioning based on signal fingerprint has always been a hot research topic. But most research requires the object or person to be positioned to carry a positioning device, which is not applicable in some special scenarios. This paper selects LoRa (Long Range) as the research target and proposes an indoor passive positioning system based on LoRa fingerprint. We design and implement the signal sent from the LoRa node devices to the LoRa gateway device and get the RSSI of the nodes, also send it to the proxy server for receiving and processing. In the data processing stage, the difference-limiting filtering algorithm is used to eliminate abnormal data, and the GaussianNB (Gaussian-Naive Bayes) algorithm is used to learn and train the model. Through experiments, the accuracy rates of the two-class and multi-class prediction in the range of 3m are 97.1% and 95.5%, respectively, which verifies the feasibility of applying LoRa signal to indoor passive positioning. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Indoor positioning systems

Smoothing Advantage Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gan, Yaozhong Zhang, Zhe Tan, Xiaoyang College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

Advantage learning (AL) aims to improve the robustness of value-based reinforcement learning against estimation errors with action-gap-based regularization. Unfortunately, the method tends to be unstable in the case of function approximation. In this paper, we propose a simple variant of AL, named smoothing advantage learning (SAL), to alleviate this problem. The key to our method is to replace the original Bellman Optimal operator in AL with a smooth one so as to obtain more reliable estimation of the temporal difference target. We give a detailed account of the resulting action gap and the performance bound for approximate SAL. Further theoretical analysis reveals that the proposed value smoothing technique not only helps to stabilize the training procedure of AL by controlling the trade-off between convergence rate and the upper bound of the approximation errors, but is beneficial to increase the action gap between the optimal and sub-optimal action value as well. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Ye Chen, Song-Can Huang, Sheng-Jun College of Computer Science and Technology/Artificial Intelligence Nanjing University of Aeronautics Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems, but they are still trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit stochastic gradient descent (ISGD) method to train PINNs for improving the stability of training process. We heuristically analyze how ISGD overcome stiffness in the gradient flow dynamics of PINNs, especially for problems with multi-scale solutions. We theoretically prove that for two-layer fully connected neural networks with large hidden nodes, randomly initialized ISGD converges to a globally optimal solution for the quadratic loss function. Empirical results demonstrate that ISGD works well in practice and compares favorably to other gradient-based optimization methods such as SGD and Adam, while can also effectively address the numerical stiffness in training dynamics via gradient descent. Copyright © 2023, The Authors. All rights reserved.

关键词： Stiffness

All Beings Are Equal in Open Set Recognition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Chaohua Zhang, Enhao Geng, Chuanxing Chen, Songcan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

In open-set recognition (OSR), a promising strategy is exploiting pseudo-unknown data outside given K known classes as an additional K+1-th class to explicitly model potential open space. However, treating unknown classes without distinction is unequal for them relative to known classes due to the category-agnostic and scale-agnostic of the unknowns. This inevitably not only disrupts the inherent distributions of unknown classes but also incurs both class-wise and instance-wise imbalances between known and unknown classes. Ideally, the OSR problem should model the whole class space as K+∞, but enumerating all unknowns is impractical. Since the core of OSR is to effectively model the boundaries of known classes, this means just focusing on the unknowns nearing the boundaries of targeted known classes seems sufficient. Thus, as a compromise, we convert the open classes from infinite to K, with a novel concept Target-Aware Universum (TAU) and propose a simple yet effective framework Dual Contrastive Learning with Target-Aware Universum (DCTAU). In details, guided by the targeted known classes, TAU automatically expands the unknown classes from the previous 1 to K, effectively alleviating the distribution disruption and the imbalance issues mentioned above. Then, a novel Dual Contrastive (DC) loss is designed, where all instances irrespective of known or TAU are considered as positives to contrast with their respective negatives. Experimental results indicate DCTAU sets a new state-of-the-art. Copyright © 2024, The Authors. All rights reserved.

关键词： machine learning

TimeCHEAT: A Channel Harmony Strategy for Irregularly Sampled Multivariate Time Series analysis

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Jiexi Cao, Meng Chen, Songcan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

Irregularly sampled multivariate time series (ISMTS) are prevalent in reality. Due to their non-uniform intervals between successive observations and varying sampling rates among series, the channel-independent (CI) strategy, which has been demonstrated more desirable for complete multivariate time series forecasting in recent studies, has failed. This failure can be further attributed to the sampling sparsity, which provides insufficient information for effective CI learning, thereby reducing its capacity. When we resort to the channel-dependent (CD) strategy, even higher capacity cannot mitigate the potential loss of diversity in learning similar embedding patterns across different channels. We find that existing work considers CI and CD strategies to be mutually exclusive, primarily because they apply these strategies to the global channel. However, we hold the view that channel strategies do not necessarily have to be used globally. Instead, by appropriately applying them locally and globally, we can create an opportunity to take full advantage of both strategies. This leads us to introduce the Channel Harmony ISMTS Transformer (TimeCHEAT), which utilizes the CD strategy locally and the CI strategy globally. Specifically, we segment the ISMTS into sub-series level patches. Locally, the CD strategy aggregates information within each patch for time embedding learning, maximizing the use of relevant observations while reducing long-range irrelevant interference. Here, we enhance generality by transforming embedding learning into an edge weight prediction task using bipartite graphs, eliminating the need for special prior knowledge. Globally, the CI strategy is applied across patches, allowing the Transformer to learn individualized attention patterns for each channel. Experimental results indicate our proposed TimeCHEAT demonstrates competitive state-of-the-art performance across three mainstream tasks including classification, forecasting and interpolation. Copyri

关键词： Time series analysis